web3-ux-feedback

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). The workflow fetches and extracts visible text from a user-provided landing page URL (outsider-authored web content) in scripts/main_tool.py, then passes the extracted text to the LLM for analysis.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.80). The skill's runtime tool (scripts/main_tool.py) performs requests.get(url) on a user-supplied landing-page URL (example shown as https://yourproject.xyz) and then injects the fetched page text into the agent analysis, meaning external content fetched at runtime can directly influence the agent's prompts/inputs.